Observability for any agent, anywhere: Production-ready tracing with OpenTelemetry & Unity Catalog on Databricks

Databricks enables storing OpenTelemetry AI traces in Unity Catalog as Delta tables, improving observability for production AI agents.

• •Real-time trace ingestion with long-term retention at lower cost than SaaS platforms
• •SQL-based analytics, PII masking governance, and MLflow evaluation integration
• •Zerobus Ingest provides serverless managed ingestion supporting standard OTLP protocols
• •LangGraph agents auto-capture model calls and tool invocations via mlflow.autolog()
• •Trace data enables ad-hoc analysis, custom dashboards, ETL pipelines, and continuous quality improvement

This summary was automatically generated by AI based on the original article and may not be fully accurate.